256 citations · 296 across the 9 of their papers we have counts for
9 papers
Efficient Visual Question Answering Pipeline for Autonomous Driving via Scene Region Compression
Yuliang Cai, Dongqiangzi Ye, Zitian Chen +1
Autonomous driving increasingly relies on Visual Question Answering (VQA) to enable vehicles to understand complex surroundings by analyzing visual inputs and textual queries. Curr…
An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training
Zitian Chen, Mingyu Ding, Yikang Shen +4
We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Despite considerable progress in multi-task learning, most effor…
Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention
Mingyu Ding, Yikang Shen, Lijie Fan +5
Humans possess a versatile mechanism for extracting structured representations of our visual world. When looking at an image, we can decompose the scene into entities and their par…
Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners
Zitian Chen, Yikang Shen, Mingyu Ding +4
Optimization in multi-task learning (MTL) is more challenging than single-task learning (STL), as the gradient from different tasks can be contradictory. When tasks are related, it…
Shot in the Dark: Few-Shot Learning with No Base-Class Labels
Zitian Chen, Subhransu Maji, Erik Learned-Miller
Few-shot learning aims to build classifiers for new classes from a small number of labeled examples and is commonly facilitated by access to examples from a distinct set of 'base c…
Cross-Supervised Object Detection
Zitian Chen, Zhiqiang Shen, Jiahui Yu +1
After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, buildi…